Innovations Neuromorphic Intelligent Visual System
■Technology Introduction
  1. Low-Power Processing-in-sensor CMOS Image Sensor
  2. Implementation of Low-Power and Low-Latency Deep Learning Chip based on Neuromorphic Intelligence.
  3. Development of Neuromorphic Chip based on The Fruit Fly Visual and Spatial Sensory Systems
  4. Hardware-Software Co-Design for Neuromorphic AI Chips.
■Scientific Innovation
  1. The computational CMOS image sensor (C2IS) with array-parallel computing can perform always-on feature extraction.
  2. Multi-precision computing in SRAM increases the DNN accuracy and performance.
  3. Based on real NN to design a low power object tracking neuromorphic chip with learning rule.
  4. FlexNet resolves the issue that incurs > 30% extra accuracy loss when changing the bit width of AI chips at run time.
■This technology won the Futuretech Breakthrough Award in 2019 Future Tech Expo. 

National Tsing Hua University

Neuromorphic Intelligent Visual System